An hybrid MLP-SVM handwritten digit recognizer

This paper presents an original hybrid MLP-SVM method for unconstrained handwritten digits recognition. Specialized support vector machines (SVMs) are introduced to improve significantly the multilayer perceptron (MLP) performances in local areas around the separation surfaces between each pair of digit classes, in the input pattern space. This hybrid architecture is based on the idea that the correct digit class almost systematically belongs to the two maximum MLP outputs and that some pairs of digit classes constitute the majority of MLP substitutions (errors). Specialized local SVMs are introduced to detect the correct class among these two classification hypotheses. The hybrid MLP-SVM recognizer achieves a recognition rate of 98.01%, for real mail zip code digits recognition task, a performance better than several classifiers reported in recent researches.

[1]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[2]  Ching Y. Suen,et al.  A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[4]  Léon Bottou,et al.  Local Learning Algorithms , 1992, Neural Computation.

[5]  Louis Vuurpijl,et al.  TWO-STAGE CHARACTER CLASSIFICATION: A COMBINED APPROACH OF CLUSTERING AND SUPPORT VECTOR CLASSIFIERS , 2000 .

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[8]  Kevin W. Bowyer,et al.  Combination of multiple classifiers using local accuracy estimates , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[10]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.